Banana Plant Disease Classification Using Hybrid Convolutional Neural Network.

Area of Science:

• Agricultural Science
• Computer Science
• Plant Pathology

Background:

• Banana cultivation is a key agricultural sector in India, facing significant threats from various diseases.
• Pest and disease detection is crucial for preventing crop loss and economic damage to farmers.
• Current methods may lack the speed and accuracy needed for timely intervention.

Purpose of the Study:

• To develop an automated system for early detection and classification of banana diseases.
• To assist farmers in identifying diseases and applying appropriate fertilizers to mitigate crop damage.
• To improve the accuracy of disease detection compared to existing deep learning techniques.

Main Methods:

• Implementation of a hybrid Convolutional Neural Network (CNN) model.
• Training the CNN on a dataset of banana crop images to identify disease indicators.
• Utilizing the model for disease detection and classification in real-time or near real-time.

Main Results:

• The proposed hybrid CNN model achieved a high accuracy rate of 99% in detecting and classifying banana diseases.
• The system provides timely disease identification, enabling farmers to take prompt action.
• Demonstrated superior performance compared to other related deep learning approaches.

Conclusions:

• The hybrid CNN model offers a highly accurate and efficient solution for banana disease management.
• This technology can significantly reduce financial losses for farmers and enhance banana productivity.
• Early disease detection through AI is vital for sustainable agriculture and economic stability.